# Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks

**Authors:** Shivang Agarwal, Jean Ogier Du Terrail, Frédéric Jurie  
**arXiv:** [1809.03193](https://arxiv.org/abs/1809.03193)  
**Date:** 2018-09-10  
**Summary page:** https://www.summarizepaper.com/en/paper/1809.03193v2/

## Key points

- Object detection is a crucial task in computer vision
- Deep convolutional neural networks (DCNN) have led to significant advances in object detection over the past five years
- The article "Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks" reviews the latest literature on object detection with deep CNNs
- The survey covers typical architectures such as SSD, YOLO and Faster-RCNN
- The article also discusses current challenges faced by the community and potential ways to extend object detection beyond its current limitations
- Public datasets and associated state-of-the-art algorithms are reviewed
- This article offers a comprehensive view of recent developments in object detection with deep CNNs
- Future directions for research in this field are highlighted.

## Summary

Object detection has become a highly important task in computer vision over the past five years, due to its relevance to many applications and the remarkable advances made in this area since the advent of deep convolutional neural networks (DCNN). In their article titled "Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks," authors Shivang Agarwal, Jean Ogier Du Terrail, and Frédéric Jurie review the latest literature on object detection with deep CNNs. The survey provides an extensive overview of recent advances, covering typical architectures such as SSD, YOLO and Faster-RCNN as well as current challenges faced by the community and potential ways to extend object detection beyond its current limitations. Additionally, this survey reviews public datasets and associated state-of-the-art algorithms. This article offers a comprehensive view of recent developments in object detection with deep CNNs and sheds light on future directions for research in this field.